New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ingest

by superhero-tech in superhero-tech/super-brain

Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it.

MITAuto-check passedKnowledge Management

Install Ingest

skills CLI
$ npx skills add superhero-tech/super-brain --skill ingest -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install superhero-tech/super-brain ingest --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/superhero-tech/super-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/7-Skills/ingest .claude/skills/ingest && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ingest
GitHub stars
155
Token cost
~1.3k tokens
SKILL.md length
779 words
Files
2 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it.

  • Works in 7 steps: Read the source → Map it against the wiki → Check in before writing → …
  • The human drops something in the inbox
  • SKILL.md covers How to invoke, How it works, Batch mode and Daily notes, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ingest is an agent skill from superhero-tech/super-brain. Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it. Use when the human drops something in the inbox, says to process it, or wants a backlog of clippings worked through.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/page-templates.md`).

It sits in Knowledge Management, covering Email management. The repository describes itself as: Product Builder Second Brain - AI Product Heroes Edition 3. The licence is MIT.

When your agent uses it

  • The human drops something in the inbox
  • Says to process it
  • Wants a backlog of clippings worked through

Example prompts

  • “Use the ingest skill to compile a source from 2-Inbox/ into the wiki, across every page it touches, then archives it”
  • “/ingest”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Read the source
  2. Map it against the wiki
  3. Check in before writing
  4. Write the pages
  5. Update the index and log
  6. Archive the source
  7. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 0922a1a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ingest loads about 1.3k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 779 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from superhero-tech/super-brain at commit 0922a1a, republished under its MIT licence (© superhero-tech). 779 words, ~1,303 tokens.

Download SKILL.mdSave it as .claude/skills/ingest/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
ingest
description
Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it. Use when the human drops something in the inbox, says to process it, or wants a backlog of clippings worked through.

Ingest

Turn a source into wiki. Not one summary page per file - one page per concept, plus every existing page this source has something to say about.

Write wiki pages in the language the human writes in. One language per page.

How to invoke

  • "Process this", "run an ingest", "I dropped something in Inbox"
  • "Process the whole inbox" for batch mode
  • /ingest

Sources live in 2-Inbox/. If the human clips with Obsidian Web Clipper on its default settings, check Clippings/ too.

How it works

1. Read the source

End to end, before forming a view of it. Note what it is - article, thread, tutorial, transcript, note - and who wrote it.

2. Map it against the wiki

Read 4-Knowledge/index.md. Then list everything the source touches and mark each item twice.

By kind:

  • concept - an idea, framework, method or pattern
  • entity - a person, company, tool or product

By state:

  • primary - the source's main concept, gets the new or heavily updated page
  • existing - has a page already, needs an update from this source
  • new - worth its own page, does not have one yet

An entity earns a page when it appears in two or more sources, or is central to this one. A name mentioned once in passing gets a citation, not a page.

Also check 5-Raw/ - if this source has been processed before, you are updating pages, not creating them.

This list is the actual work. Everything after it is execution.

3. Check in before writing

Show the human what you found, in three or four lines: what the source argues, which pages you are about to touch, and anything in it that contradicts what the wiki already says. Then wait.

A wrong page written now is a wrong answer in every query for the next month, and nobody will notice until it has been built on. This is the cheapest place to catch it. Batch mode is the only exemption.

4. Write the pages

Load references/page-templates.md now - it has the frontmatter and the shape for both concept and entity pages.

Write the primary page first, then every page marked existing. For each of those: add what this source adds, cite it, and link to the primary page.

Link in both directions. A [[link]] from the new page to an old one is half a link. Add the return link on the old page. One-directional links are how pages become orphans.

A substantial source moves five or more pages. Touching one page and stopping turns the wiki into a pile of summaries. If a source genuinely touched one page, say so and say why - early on the honest answer is usually that the wiki is still too small.

Two rules hold on every page you touch:

  • Cite the source on every claim: [source: file-name.md]
  • Flag contradictions instead of overwriting: > CONTRADICTION: [old claim] vs [new claim] from [source]
Show full SKILL.md (304 more words)Show less
5. Update the index and log
  • 4-Knowledge/index.md: add the new pages, refresh the descriptions of changed ones. Concepts and entities are listed separately.
  • 4-Knowledge/log.md: append an ingest entry listing every page you touched, not only the primary one. That file carries the format.
6. Archive the source

Move the file from 2-Inbox/ or Clippings/ to 5-Raw/, and any images that came with it to 5-Raw/assets/. Never rename an asset afterwards - the pages referencing it will not follow.

7. Report
Processed: "file-name.md"
  -> Primary: 4-Knowledge/[Subfolder]/[Page Title].md (created)
  -> Updated: [Page B], [Page C], [Page D]
  -> Entities: [Name] (created), [Name] (updated)
  -> Worth writing later: [concept X], [entity Y]
  -> Archive: 5-Raw/

Batch mode

For a backlog, work through the files one at a time and skip the step 3 check-in. Say up front that batch mode runs unsupervised and produces thinner pages than one-at-a-time ingest, because nobody is correcting the reading.

Finish with a table of file, primary page, how many other pages moved, and the created/updated status, then the totals.

Daily notes

1-Daily/ is a source too, but never ingest it unasked - daily notes are personal, unfinished, and full of things that were true for one afternoon.

When the human asks you to go through a week or a month of them, read the range and sort what you find: anything general goes to Knowledge as an ingest, anything about a specific project goes to that project's log as an update.

Self-check

  • Every page you listed as existing was actually opened and updated
  • Every new link has its return link
  • 4-Knowledge/index.md lists the new pages, log.md lists all of them
  • The source is in 5-Raw/ and its images are in 5-Raw/assets/
  • If only one page moved, you said why

Hard constraints

  • Files in 5-Raw/ are read-only once archived. Cite them, leave them alone.
  • Contradictions get flagged, never silently resolved.
  • A source moves out of the inbox only after its pages exist.
  • Entity pages stay short and link out. The reasoning lives on the concept page.

© superhero-tech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in 7-Skills/ingest of superhero-tech/super-brain.

  • SKILL.md
  • references/page-templates.md

Open the folder on GitHubat commit 0922a1a

Compare with similar skills

Ingest next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ingest compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ingest this skillsuperhero-tech/super-brain155—~1.3kAutomated safety check: PassMIT
Weekly Review PlanningNousResearch/hermes-agent252k—~994Automated safety check: PassMIT
Para Skillaiskillstore/marketplace430—~2kAutomated safety check: PassMIT
KapsoLeeroo-AI/kapso120—~3.6kAutomated safety check: NotesMIT
Cascading Goal Trackerballred/obsidian-claude-pkm1.9k—~1.5kAutomated safety check: PassMIT
Dbrain Processorsmixs/agent-second-brain391—~3.3kAutomated safety check: PassMIT

Similar skills

  • Weekly Review Planning

    NousResearch/hermes-agent

    Weekly reset: commitments, stalled work, next-week plan. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~994 tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Para Skill

    aiskillstore/marketplace

    PARA method knowledge management for Obsidian vaults. An agent skill from aiskillstore/marketplace.

    430 GitHub stars~2k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Kapso

    Leeroo-AI/kapso

    Operate Kapso (PyPI leeroo-kapso), the long-running agents that optimize AI and Data systems, from a coding session — verify the install with kapso doctor, launch and follow an evolve campaign…

    120 GitHub stars~3.6k tokensUpdated yesterday
    Knowledge ManagementAuto-check: notes

  • Cascading Goal Tracker

    ballred/obsidian-claude-pkm

    Tracks three-year, yearly, monthly, and weekly goals in linked Markdown files, calculating completion percentages and flagging stalled goals.

    1.9k GitHub stars~1.5k tokensUpdated 7 mo ago
    Knowledge ManagementAuto-check passed

  • Dbrain Processor

    smixs/agent-second-brain

    Personal assistant for processing daily voice/text entries from Telegram.

    391 GitHub stars~3.3k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

  • Traul Message Search

    dandaka/traul

    Drives the traul CLI to sync, search and monitor messages from Slack, Telegram, Discord, Linear, Gmail, WhatsApp, Claude Code sessions and Markdown files.

    113 GitHub stars~3.9k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check: notes

More from superhero-tech/super-brain

All 8 skills in this repo

  • Second Brain Setup

    superhero-tech/super-brain

    A skill your agent uses when creating or refreshing a product builder's personal profile in 8-System/about.md - supports both assessment-based (Gallup, DISC, MBTI) and interview-based onboarding

    155 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Feynman

    superhero-tech/super-brain

    Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin.

    155 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Lint

    superhero-tech/super-brain

    Health check over the compiled wiki in 4-Knowledge/, written up as a ranked report.

    155 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Query

    superhero-tech/super-brain

    Answers from the compiled wiki in 4-Knowledge/, with citations and a saved output file.

    155 GitHub stars~909 tokensUpdated 1 mo ago
    Auto-check passed

  • Youtube

    superhero-tech/super-brain

    Captures a YouTube video as a source note and a wiki page. An agent skill from superhero-tech/super-brain.

    155 GitHub stars~985 tokensUpdated 1 mo ago
    Auto-check passed

  • Project Start

    superhero-tech/super-brain

    Sets up a new project folder and runs the interview that fills its brief.

    155 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Ingest

What does Ingest do?

Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it. Ingest is an agent skill from superhero-tech/super-brain. Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it.

When should I use Ingest?

Ingest fits situations like: the human drops something in the inbox; says to process it; wants a backlog of clippings worked through.

How do I install Ingest in Claude Code?

Run `npx skills add superhero-tech/super-brain --skill ingest -a claude-code`. Or copy the skill folder (7-Skills/ingest in superhero-tech/super-brain) into .claude/skills/ingest in your project. Claude Code loads it when a task matches its description.

How do I install Ingest in Codex?

Run `npx skills add superhero-tech/super-brain --skill ingest -a codex`. Or copy the skill folder (7-Skills/ingest in superhero-tech/super-brain) into .agents/skills/ingest in your project. Codex loads it when a task matches its description.

Can I use Ingest in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add superhero-tech/super-brain --skill ingest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ingest, .gemini/skills/ingest, .github/skills/ingest and .opencode/skills/ingest in your project.

What does Ingest need to run?

SKILL.md names no scripts, command-line tools or credentials: Ingest is instructions for the agent only.

Does Ingest access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ingest safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ingest use?

Ingest is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ingest use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 494 tokens, read only when the agent opens those files.

What are the alternatives to Ingest?

Skills that share tags, products or a category with Ingest: Weekly Review Planning (NousResearch/hermes-agent, 252k stars), Para Skill (aiskillstore/marketplace, 430 stars), Kapso (Leeroo-AI/kapso, 120 stars) and Cascading Goal Tracker (ballred/obsidian-claude-pkm, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ingest?

superhero-tech (a GitHub organization) maintains it in superhero-tech/super-brain, which has 155 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 25, 2026.

Source: superhero-tech/super-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.